SUI

https://arxiv.org/abs/2305.16867 Playing repeated games with Large Language Models Large Language Models (LLMs) are transforming society and permeating into diverse applications. As a result, LLMs will frequently interact with us and other agents. It is, therefore, of great societal value to understand how LLMs behave in interactive soci arxiv.org 1. 대규모 언어 모델(LLMs)이 사회를 변화시키고 다양한 응용 분야에 퍼지고 있습니..

https://arxiv.org/abs/2305.17100 BiomedGPT: A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks In this paper, we introduce a unified and generalist Biomedical Generative Pre-trained Transformer (BiomedGPT) model, which leverages self-supervision on large and diverse datasets to accept multi-modal inputs and perform a range of downstr..

https://panda-gpt.github.io/ PandaGPT PandaGPT is a general-purpose instruction-following model that can both see and hear. Our pilot experiments show that PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questi panda-gpt.github.io https://arxiv.org/abs/2305.16355 PandaGPT: One Model To Instruction-Follow Them All..

https://arxiv.org/abs/2305.16338 Think Before You Act: Decision Transformers with Internal Working Memory Large language model (LLM)-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and compute. We argue that this inefficiency stems from the forgetting phenomenon, in whic arxiv.org 1. 대형 언어 모델(LLM) 기반의 결정 생..

https://arxiv.org/abs/2305.14342 Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training. Adam and its variants have been state-of-the-art for years, and more sophist arxiv.org https://twitt..

https://www.quantamagazine.org/some-neural-networks-learn-language-like-humans-20230522/ Some Neural Networks Learn Language Like Humans | Quanta Magazine Researchers uncover striking parallels in the ways that humans and machine learning models acquire language skills. www.quantamagazine.org 뇌와 인공 신경망이 어떻게 학습하는지는 여전히 미스터리입니다. 그러나 최근의 연구는 인공 신경망과 인간이 언어를 배우는 방식이 유사할 수 있다는 놀라운 결과를 보여줍니다. 연구자들은 "b..

https://thequantuminsider.com/2023/05/23/ibm-aims-for-100000-qubit-machine-by-2033-pioneering-quantum-centric-supercomputing IBM Aims for 100,000-Qubit Machine by 2033, Pioneering 'Quantum-Centric Supercomputing' IBM is setting its sights on a 100,000-qubit quantum-centric supercomputer within a decade, according to a statement. thequantuminsider.com IBM이 2033년까지 100,000큐비트 규모의 양자 중심 슈퍼컴퓨터를 개발하는..

https://twitter.com/CSERCambridge/status/1661777454212546561?s=20 트위터에서 즐기는 Centre for the Study of Existential Risk “Geoffrey Hinton's lecture will be starting in about 10 minutes. "Two Paths to Intelligence" has already filled up the lecture theatre here. Follow along with us for the key insights! Organised along with @LeverhulmeCFI, @Cambridge_Eng, and @CSERCambridg twitter.com 제프리 힌튼은 이제 역전파..